CN112820123B - Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp - Google Patents
Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp Download PDFInfo
- Publication number
- CN112820123B CN112820123B CN202110015443.8A CN202110015443A CN112820123B CN 112820123 B CN112820123 B CN 112820123B CN 202110015443 A CN202110015443 A CN 202110015443A CN 112820123 B CN112820123 B CN 112820123B
- Authority
- CN
- China
- Prior art keywords
- speed
- processor
- timer
- time
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
Abstract
The invention has disclosed a traffic signal lamp green wave intelligent regulation method and intelligent regulation system, set up the communication connection with the traffic signal lamp system through the first communication module, the first communication module receives the operational data of the traffic signal lamp of the crossing, send to the first processor, the first processor sends the operational data of the said traffic signal lamp to the storage module to keep; the speed measuring module measures the speed of the vehicle in real time and sends the speed information and the time information to the first processor; the camera module identifies the license plate number of the vehicle and sends the license plate information to the first processor; the first processor packages and sends data to the second processor after receiving the information of the speed, the time and the license plate number, the second processor carries out speed prediction and flow analysis according to the received data, and decides the crossing passing result in the traffic light state period according to the flow analysis result. The green wave speed per hour can be adjusted in real time, and the traffic efficiency is maximized.
Description
The invention relates to a divisional application of an invention patent with the application number of 2020108741318, wherein the application number is 'green wave intelligent regulation method and intelligent regulation system of a traffic signal lamp'.
Technical Field
The application belongs to the field of computers and intellectualization, and particularly relates to a green wave intelligent adjusting system of a traffic signal lamp and a using method thereof.
Background
The green wave traffic is that a set of automatically controlled linkage signals with a certain period are installed on a series of intersections, so that the traffic flow on the main road meets green lights when arriving at each intersection in front in sequence. The green wave traffic reduces the stop of vehicles at the intersection and improves the average driving speed and traffic capacity. The reasonable green wave passing has very important significance for remarkably improving the road passing efficiency and relieving traffic jam, and meanwhile, the efficient passing has obvious effects on energy conservation and emission reduction.
The technical scheme of the prior art for green wave passing is to set a section of green wave band, calculate a determined green wave speed according to the traffic light interval and the road section length in the green wave band, and use the determined green wave speed as the guide of all passing vehicles. However, the prior art has the defects that: only one uniform green wave speed can be given, but the green wave speed can not be generally reached when the vehicle slowly travels in a traffic peak, so that the green wave traffic fails, the red light of some vehicles is at the bottom, the traffic efficiency is seriously influenced, and the emission is increased.
Disclosure of Invention
The invention provides an intelligent green wave adjusting system of a traffic signal lamp and a using method thereof, aiming at solving the technical problems that the traffic efficiency is seriously influenced and the emission is increased because only one uniform green wave speed is available at present and the green wave speed can not be generally reached when a vehicle passes through a slow running peak, so that the green wave speed can be adjusted in real time according to the macroscopic traffic condition, the green wave adjustment is realized, and the traffic efficiency is maximized.
The technical scheme of the invention is as follows:
an intelligent green wave adjusting method for a traffic signal lamp comprises the following steps:
the first communication module receives the operation data of the intersection traffic signal lamp and then sends the operation data to the first processor, and the first processor sends the operation data of the traffic signal lamp to the storage module for storage;
the speed measuring module connected to the first interface module measures the speed of the vehicle in real time and sends the speed information and the time information to the first processor; the first interface module is also connected with a camera module for identifying the license plate number of the vehicle and sending the license plate number information to the first processor;
the first processor receives the information of the speed, the time and the license plate number and packs the data into a whole
Wherein i represents the count of the vehicle, i is an integer greater than 0, i is the vehicle i, t represents the data time, and D represents the data packet;
representing the number plate of vehicle i identified at time t,
representing the speed measurement sequence of the vehicle i at the time t; the first processor transmits data packets
Sending to the second processor, the second processor operating the multi-target speed prediction program based on the received
And predicting the speed of the data, analyzing the flow based on the speed prediction, and deciding the crossing passing result in the traffic light state period according to the flow analysis result.
Further, the speed measuring module measures speed by using a speed measuring sequence, that is, the speed measuring module measures speed of n sequences for the vehicle at a time interval Δ t to obtain a speed measuring sequence of a target vehicle i in a state of time t
n>2 is an integer.
Further, the specific steps of the second processor for multi-target speed prediction and flow analysis based on the speed prediction are as follows:
s1, establishing a fitting prediction network related to the vehicle speed prediction time of the target vehicle;
s2, analyzing the flow of each intersection at the future time in real time based on the speed prediction;
s3, according to the flow analysis result, deciding the crossing passing result in the traffic light state period.
Further, in step S1, the fitting prediction network is established as follows:
establishing a four-layer neural network, wherein the four-layer neural network comprises an input layer, a first middle layer, a second middle layer and an output layer, the input layer and the first middle layer are respectively composed of a neuron, the second middle layer is provided with n neurons, n is equal to the dimension of a speed measurement sequence, the output layer is composed of a neuron, the input is a time variable, and the output is a predicted speed value.
The second intermediate layer is also provided with input excitation, so that the n-dimensional speed measurement sequence of the target vehicle i at the time t state
Is an input stimulus;
the connection weight of the input layer and the first intermediate layer is recorded as w12And the connection weight of the first intermediate layer and the second intermediate layer is recorded as w2x(x is more than or equal to 1 and less than or equal to n), and the connection weight of the second intermediate layer and the output layer is recorded as w3q(q is more than or equal to 1 and less than or equal to n). The threshold of the network neuron adopts a unified threshold control method, and when the input excitation is not fully 0, the representative neuron meets the output threshold.
Further, the calculation process of the fitting prediction network is as follows:
the input is tmAnd when the input excitation is not all 0, the output of the input layer neuron is f1(tm)·w12Wherein f is1(d) D is a function argument for the activation function of the input layer, as an embodiment of the present invention, it is possible to have
The output of the input layer neuron is noted as f1o(tm) Then there is
Output of input layer neurons f1O(tm) I.e. the input of the first intermediate layer, the output of the first intermediate layer is denoted f2O(tm) Then there is f2O(tm)＝f2(f1O)·w2xWherein f is2Representing an activation function of the first intermediate layer; as an example of the present invention, a,
then there is
The output and input excitation of each neuron of the first intermediate layer jointly participate in the calculation of the second intermediate layer, and the output of the neuron of the second intermediate layer is recorded as yj(m), (j is more than or equal to 1 and less than or equal to n); then there are:
the last output of the output layer neurons is recorded as
Further, the specific method of step S2 is as follows:
when the second processor receives the data packet from the first processor
The second processor analyzes the time t and the speed measuring sequence in the data packet
And predicts the time (t + delta t) and the velocity measurement sequence is
The target speed in the state is recorded as
For any intersection r, the labels in four directions are sequentially set as 1,2,3 and 4, and the distances from the green wave intelligent adjusting system equipment to the intersection stop line in the corresponding directions are sequentially
Respectively calculating the estimated time required by the target vehicles in 4 directions to reach the stop line of the intersection:
wherein the content of the first and second substances,
respectively representing the estimated time required for the target vehicles in the directions 1,2,3 and 4 to reach the stop line of the intersection,
representing the estimated speeds of the target vehicles in directions 1,2,3 and 4 at (t + Δ t), respectively;
for the direction 1 of the intersection r, the parameters of the target vehicle i
Speed measurement sequence
The prediction network established in the step of inputting S1 predicts the speed at which the target vehicle i moves to the stop line
The average speed of the target vehicle i moving from the speed measurement point to the stop line
The target vehicle i reaches the stop line at a time of
Similarly, the times of the target vehicles reaching the stop line in other 3 directions of the intersection r can be respectively calculated as
Recording the state period of r traffic lights at the intersection as TrThe flow analysis of the intersection r at the future time is as follows:
in the second processor, 4 counters Timer are set1、Timer2、Timer3、Timer4For counting the flow in 4 directions;
for direction 1, in one traffic light state period
Then Timer1＝Timer1+ + where Timer1+ represents the self-increment of the counter by 1 when
Timer1Keeping the same;
similarly, the flow in other 3 directions can be analyzed, and the counting period of the 4 counters is TrWhen the count period exceeds TrThen, the 4 counters are cleared and counted again, and flow analysis of the next period is carried out;
recording in a counting period, and finally, the flow counts in 4 directions are respectively Timer1、Timer2、Timer3、Timer4And then the flow analysis of 4 directions of the intersection r in the counting period is completed.
Further, the step S3 decides the passing result of the intersection in the traffic light state period based on the flow analysis result of the step S2, and the process is as follows:
when max (Timer)1,Timer3)>max(Timer2,Timer4) When the vehicle is running, the directions 1 and 3 of the intersection r are in a passing state, and the directions 2 and 4 are in a forbidden state;
when max (Timer)1,Timer3)≤max(Timer2,Timer4) When the vehicle is running, the directions 1 and 3 of the intersection r are in a forbidden state, and the directions 2 and 4 are in a passing state; where max (,) represents taking a larger value;
take max (Timer)1,Timer2,Timer3,Timer4) Counter, future moment corresponding to last valid count
As the green wave adjustment time in the present counting period, the input parameter of the target vehicle i
Sum velocity sequence
The predicted network input to step S1 can output the speed
Then the
Is the green wave suggested speed for target vehicle i;
the second processor will
Sending to the first processor, the first processor will
Sending to the second communication module
Broadcast to target vehicle i.
Further, the second processor will also time (b)
) Sent to the first processor, the first processor will: (
) And the second interface module is used for sending the time to the display module for displaying so as to remind the time of the green light state of the target vehicle.
An intelligent green wave adjusting system for traffic signals and the like comprises a first communication module, a first processor, a second processor, a first interface module, a speed measuring module, a camera module, a second interface module, a display module, a second communication module and a storage module;
the first communication module is mainly used for communicating with systems such as traffic signals and the like, and can receive traffic light operation data sent by a traffic light system and send control signals to a traffic signal light control system; the first communication module is connected with a first processor;
the first processor is mainly used for processing data transmitted by each module in the traffic signal and other green wave intelligent adjusting system and performing data interaction with each module, and the first processor is connected with a second processor, a first interface module, a second communication module and a storage module;
the second processor runs a multi-target speed prediction and flow analysis program, can quickly predict a plurality of target vehicle speeds and carries out intersection flow analysis based on the speed prediction;
the first interface module is used for connecting speed measuring and image collecting equipment, and is connected with a speed measuring module and a camera module;
the speed measuring module is used for measuring the speed of a moving target including a vehicle and sending speed measuring data to the first processor through the first interface module;
the camera module is used for shooting and identifying the license plate number and sending the data to the first processor through the first interface module;
the second interface module is used for connecting and transmitting data to the display module;
the display module is mainly used for displaying the intelligently adjusted suggested green wave speed;
the second communication module is mainly used for receiving the data sent by the first processor and differentially broadcasting the suggested green wave speed to the peripheral vehicles;
the storage module is mainly used for storing the operation data of the traffic signal lamp, the vehicle speed, the license plate number and the image data.
Further, the operation data of the signal lamp comprises the current operation mode of the traffic light, the working period of the red light, the yellow light and the green light, the current traffic light state, the state remaining time and the next state data.
The invention has at least the following beneficial effects:
(1) the invention adopts the technical scheme that a speed measuring module measures the speed of a vehicle in real time and sends vehicle speed information and time information to a first processor, a camera module identifies the license plate number of the vehicle and sends the license plate number information to the first processor, and the first processor sends a data packet
Sending to the second processor, the second processor operating the multi-target speed prediction program based on the received
The data is subjected to speed prediction, flow analysis is carried out based on the speed prediction, and a traffic light state period road crossing passing result is decided according to the flow analysis result, so that the speed can be measured in real time and the speed prediction can be carried out in real time through the technical scheme, and the green wave speed per hour can be adjusted in real time according to the macroscopic traffic passing condition; and the differential suggested green wave speed per hour can be pushed to different vehicles according to the driving habits of different vehicles.
(2) The invention adopts the fitting prediction network to predict the speed of the target vehicle, the prediction network has simple structure and high calculation speed, can continuously and quickly predict and output the multi-target speed in the actual working condition, and the green wave regulation decision is realized based on the speed prediction, thereby realizing the green wave regulation and simultaneously realizing the maximum traffic efficiency.
Drawings
FIG. 1 is a block diagram of an intelligent green wave adjusting system for a traffic signal lamp according to the present invention;
FIG. 2 is a schematic diagram of the operation of the intelligent green wave regulation system of the present invention in an existing traffic system;
FIG. 3 is a diagram of a fitted predictive network architecture according to the present invention.
Detailed Description
For a more clear description of the invention, reference is now made to the accompanying drawings, which together with the detailed description, serve to explain the principles of the invention.
Referring to fig. 1, the green wave intelligent regulating system for traffic signals and the like according to the present invention is composed of the following parts:
the device comprises a first communication module 10, a first processor 20, a second processor 30, a first interface module 40, a speed measuring module 50, a camera module 60, a second interface module 70, a display module 80, a second communication module 90 and a storage module 100.
Referring to fig. 2, the green wave intelligent adjusting system device composed of the modules is installed in a traffic system composed of a plurality of traffic lights, the green wave intelligent adjusting system device is installed in a road section between the traffic lights, theoretically, the greater the installation density is, the better the effect is, and by integrating actual working conditions and investment scale, at least one green wave intelligent adjusting system device should be installed between every two traffic lights.
The first communication module 10 is mainly used for communicating with systems such as traffic signals and the like, and can receive traffic light operation data sent by a traffic light system and send control signals to a traffic signal light control system; the first communication module 10 is connected to a first processor 20 via a data bus.
The first processor 20 is mainly used for processing data transmitted from each module in the system of the present invention, and performing data interaction with each module. The first processor 20 is connected to a second processor 30 via a data bus.
The second processor 30 runs a multi-target speed prediction and flow analysis program, can quickly predict a plurality of target vehicle speeds, and performs intersection flow analysis based on the speed prediction.
The first processor 20 is also connected to a first interface module 40 via a data bus.
The first interface module 40 is used for connecting speed measurement and image acquisition equipment, and the connection mode includes but is not limited to wired communication connection such as network cable, optical fiber and wireless communication connection such as bluetooth, wifi, infrared. The first interface module 40 is connected with a speed measuring module 50 and a camera module 60.
The speed measuring module 50 is configured to measure speed of a moving object including a vehicle, and send speed measurement data to the first processor 20 through the first interface module.
The camera module 60 is configured to capture and recognize a license plate number, and send data to the first processor 20 through the first interface module.
The first processor 20 is also connected to a second interface module 70 via a data bus.
The second interface module 70 is used for connecting and transmitting display data to the display module 80.
The display module 80 is mainly used for displaying the intelligently adjusted suggested green wave speed.
The first processor 20 is also connected to a second communication module 90 via a data bus.
The second communication module 90 is mainly used for receiving the data sent by the first processor and differentially broadcasting the suggested green wave speed to the surrounding vehicles;
the first processor 20 is further connected to a storage module 100 through a data bus, the storage module 100 is mainly used for storing the operation data of the traffic signal lamp and the data of the vehicle speed, the license plate number, the image and the like, and the operation data of the traffic signal lamp includes the operation data of the current operation mode of the traffic signal lamp, the operation cycle of the red light, the yellow light and the green light, the current traffic state, the state remaining time, the next state and the like.
The traffic signal lamp green wave intelligent regulating system establishes communication connection with a traffic signal lamp system through the first communication module 10, when the intelligent regulating system is initialized, the first communication module 10 receives operation data of a crossing traffic signal lamp and then sends the operation data to the first processor 20, and the first processor 20 sends the operation data of the traffic signal lamp to the storage module 100 for storage.
Speed measuring module connected to first interface module 4050, measuring the speed of the vehicle in real time and sending the speed information and the time information to the first processor 20; in order to ensure the accuracy of the subsequent vehicle speed prediction, the invention adopts a speed measurement sequence method, namely the speed measurement module 50 measures the speed of n sequences of the vehicle at the time interval delta t and obtains the speed measurement sequence of the target vehicle i in the state of time t
n>2 is an integer; the first interface module 40 is further connected with a camera module 60 for identifying the license plate number of the vehicle and sending the license plate number information to the first processor 20. The first processor 20 receives the speed, time and number information and packs the data into
Wherein i represents the count of vehicles, i is an integer greater than 0, i.e., vehicle i; t represents a data time; d represents a data packet;
the license plate number of the vehicle i identified at the moment t is shown;
representing the tachometric sequence of the vehicle i at time t. The first processor 20 will package the data
Sent to the second processor 30, and the second processor 30 may run a multi-target speed prediction program based on the received information
The data is subjected to speed prediction, and flow analysis is carried out based on the speed prediction, wherein the specific processing process comprises the following steps:
in order to reduce the influence of the sudden change acceleration of the vehicle on the speed prediction accuracy to the maximum extent, the invention provides a fitting prediction network, and the method is shown in figure 3.
S1, establishing a fitting prediction network related to the target vehicle speed prediction time.
Establishing a four-layer neural network, as shown in fig. 3, the four-layer neural network includes an input layer, a first intermediate layer, a second intermediate layer and an output layer, the input layer and the first intermediate layer each include a neuron, the second intermediate layer includes n neurons, n is equal to the dimension of a velocity measurement sequence, the output layer includes a neuron, the input is a time variable, and the output is a predicted velocity value.
The second intermediate layer is also provided with input excitation, so that the n-dimensional speed measurement sequence of the target vehicle i at the time t state
Is the input stimulus.
The connection weight of the input layer and the first intermediate layer is recorded as w12And the connection weight of the first intermediate layer and the second intermediate layer is recorded as w2x(x is more than or equal to 1 and less than or equal to n), and the connection weight of the second intermediate layer and the output layer is recorded as w3q(q is more than or equal to 1 and less than or equal to n). The threshold of the network neuron adopts a unified threshold control method, and when the input excitation is not fully 0, the representative neuron meets the output threshold.
The calculation process of the prediction network is as follows:
the input is tmAnd when the input excitation is not all 0, the output of the input layer neuron is f1(tm)·w12Wherein f is1(d) D is a function argument for the activation function of the input layer, as an embodiment of the present invention, it is possible to have
The output of the input layer neuron is noted as f1O(tm) Then there is
Output of input layer neurons f1O(tm) I.e. the input of the first intermediate layer, the output of the first intermediate layer is denoted f2O(tm) Then there is f2O(tm)＝f2(f1O)·w2xWherein f is2Representing the activation function of the first intermediate layer. As an example of the present invention, a,
then there is
In the above activation function, e is common knowledge and denotes the base of the natural logarithm.
The output and input excitation of each neuron of the first intermediate layer jointly participate in the calculation of the second intermediate layer, and the output of the neuron of the second intermediate layer is recorded as yj(m), (j is more than or equal to 1 and less than or equal to n); then there are:
the last output of the output layer neurons is recorded as
The prediction network has the advantages that: the device has the advantages of simple structure and high calculation speed, and can continuously and quickly carry out prediction output on multi-target speed in actual working conditions.
S2 analyzes the traffic of each intersection at the future time in real time based on the speed prediction.
When the second processor 30 receives the data packet from the first processor 20
The second processor 30 resolves the time t and velocity sequence into a data packet
And predicts the time (t + delta t) and the velocity measurement sequence is
The target speed in the state is recorded as
Referring to fig. 2, for any intersection r, the labels in four directions are 1,2,3 and 4 in sequence, and the distances from the green wave intelligent regulating system equipment to the intersection stop line in the corresponding directions are 1
Respectively calculating the estimated time required by the target vehicles in 4 directions to reach the stop line of the intersection:
wherein the content of the first and second substances,
respectively representing the estimated time required for the direction 1,2,3,4 target vehicles to reach the intersection stop line.
Representing the estimated speeds of the target vehicles in directions 1,2,3,4 at (t + Δ t), respectively.
For the direction 1 of the intersection r, the parameters of the target vehicle i
Speed measurement sequence
The prediction network established in the step of inputting S1 predicts the speed at which the target vehicle i moves to the stop line
The average speed of the target vehicle i moving from the speed measurement point to the stop line
Target vehicle i arrivesThe time of stopping the line is
Similarly, the times of the target vehicles reaching the stop line in other 3 directions of the intersection r can be respectively calculated as
Recording the state period of r traffic lights at the intersection as TrThe flow analysis of the intersection r at the future time is as follows:
in the second processor 30, 4 counters Timer are set1、Timer2、Timer3、Timer4For counting the flow in 4 directions.
For direction 1, in one traffic light state period
Then Timer1＝Timer1+ + where Timer1And + represents the counter self-incrementing by 1. When in use
Timer1Remain unchanged.
Similarly, the flow in other 3 directions can be analyzed, and the counting period of the 4 counters is TrWhen the count period exceeds TrAnd (4) clearing and recounting the counters, and entering flow analysis of the next period.
Recording in a counting period, and finally, the flow counts in 4 directions are respectively Timer1、Timer2、Timer3、Timer4And then the flow analysis of 4 directions of the intersection r in the counting period is completed.
S3, according to the flow analysis result, deciding the crossing passing result in the traffic light state period.
And (4) determining a passing result of the intersection in the traffic light state period based on the flow analysis result in the step S2, wherein the process is as follows:
when max (Timer)1,Timer3)>max(Timer2,Timer4) At this time, the directions 1 and 3 of the intersection r are in the traffic state, and the directions 2 and 4 are in the no-go state.
When max (Timer)1,Timer3)≤max(Timer2,Timer4) At this time, the directions 1 and 3 of the intersection r are in the no-go state, and the directions 2 and 4 are in the pass state.
Where max (,) represents taking a larger value.
Take max (Timer)1,Timer2,Timer3,Timer4) Counter, future moment corresponding to last valid count
As the green wave adjustment time in the present counting period, the input parameter of the target vehicle i
Sum velocity sequence
The predicted network input to step S1 can output the speed
Then the
Is the green wave suggested speed for the target vehicle i.
The second processor 30 will
Sent to the first processor 20, and the first processor 20 will send
Sent to the second communication module 90, and the second communication module 90 will send
Broadcast to target vehicle i.
The second processor 30 will also time of day
Sent to the first processor 20, and the first processor 20 will send
The green light is sent to the display module 80 through the second interface module 70 for displaying, so as to remind the target vehicle of the time of the green light state.
In conclusion, the green wave intelligent adjusting system of the traffic signal lamp is realized.
It should be understood that the above are only preferred embodiments of the present invention, and any modification made based on the spirit of the present invention should be within the scope of the present invention.
Claims (3)
1. An intelligent green wave adjusting method for a traffic signal lamp is characterized by comprising the following steps:
the first communication module receives the operation data of the intersection traffic signal lamp and then sends the operation data to the first processor, and the first processor sends the operation data of the traffic signal lamp to the storage module for storage;
the speed measuring module connected to the first interface module measures the speed of the vehicle in real time and sends the speed information and the time information to the first processor; the first interface module is also connected with a camera module for identifying the license plate number of the vehicle and sending the license plate number information to the first processor;
the first processor receives the information of the speed, the time and the license plate number and packs the data into a whole
Where i denotes the vehicle count, i is an integer greater than 0, i.e. vehicle i, t denotes the data time, D denotes the dataPackaging;
representing the number plate of vehicle i identified at time t,
representing the speed measurement sequence of the vehicle i at the time t; the first processor transmits data packets
Sending to the second processor, the second processor operating the multi-target speed prediction program based on the received
Carrying out speed prediction on the data, carrying out flow analysis based on the speed prediction, and deciding a crossing passing result in a traffic light state period according to a flow analysis result;
the speed measuring module adopts a speed measuring sequence method when measuring speed, namely the speed measuring module measures speed of n sequences for the vehicle at a time interval delta t and obtains the speed measuring sequence of a target vehicle i in a state of time t
n>2 is an integer;
the second processor performs multi-target speed prediction and flow analysis based on the speed prediction, and the specific steps are as follows:
s1, establishing a fitting prediction network related to the vehicle speed prediction time of the target vehicle;
s2, analyzing the flow of each intersection at the future time in real time based on the speed prediction;
s3, deciding the crossing passing result in the traffic light state period according to the flow analysis result;
the specific method of step S2 is as follows:
when the second processor receives the data packet from the first processor
The second processor analyzes the time t and the speed measuring sequence in the data packet
And predicts the time (t + delta t) and the velocity measurement sequence is
The target speed in the state is recorded as
For any intersection r, the labels in four directions are sequentially set as 1,2,3 and 4, and the distances from the intelligent green wave adjusting system equipment to the intersection stop line in the corresponding directions are sequentially
Respectively calculating the estimated time required by the target vehicles in 4 directions to reach the stop line of the intersection:
wherein the content of the first and second substances,
respectively representing the estimated time required for the target vehicles in the directions 1,2,3 and 4 to reach the stop line of the intersection,
representing the estimated speeds of the target vehicles in directions 1,2,3 and 4 at (t + Δ t), respectively;
for the direction 1 of the intersection r, the parameters of the target vehicle i
Speed measuring sequence
The prediction network established in the step of inputting S1 predicts the speed at which the target vehicle i moves to the stop line
The average speed of the target vehicle i moving from the speed measurement point to the stop line
The target vehicle i reaches the stop line at a time of
Similarly, the times of the target vehicles reaching the stop line in other 3 directions of the intersection r can be respectively calculated as
Recording the state period of r traffic lights at the intersection as TrThe flow analysis of the intersection r at the future time is as follows:
in the second processor, 4 counters Timer are set1、Timer2、Timer3、Timer4For counting the flow in 4 directions;
for direction 1, in one traffic light state period
Then Timer1＝Timer1+ + where Timer1+ represents the self-increment of the counter by 1 when
Timer1Keeping the same;
similarly, the flow in other 3 directions can be analyzed, and the counting period of the 4 counters is TrWhen the count period exceeds TrThen, the 4 counters are cleared and counted again, and flow analysis of the next period is carried out;
recording in a counting period, and finally, the flow counts in 4 directions are respectively Timer1、Timer2、Timer3、Timer4Then, the flow analysis of 4 directions of the intersection r in the counting period is completed;
the step S3 decides the passing result of the intersection in the traffic light state period based on the flow analysis result of the step S2, and the process is as follows:
when max (Timer)1,Timer3)>max(Timer2,Timer4) When the vehicle is running, the directions 1 and 3 of the intersection r are in a passing state, and the directions 2 and 4 are in a forbidden state;
when max (Timer)1,Timer3)≤max(Timer2,Timer4) When the vehicle is running, the directions 1 and 3 of the intersection r are in a forbidden state, and the directions 2 and 4 are in a passing state; where max (,) represents taking a larger value;
take max (Timer)1,Timer2,Timer3,Timer4) Counter, future moment corresponding to last valid count
As the green wave adjustment time in the present counting period, the input parameter of the target vehicle i
Sum velocity sequence
The predicted network input to step S1 can output the speed
Then the
Is the green wave suggested speed for target vehicle i;
the second processor will
Sending to the first processor, the first processor will
Sending to the second communication module
Broadcast to target vehicle i.
2. The intelligent green wave adjusting method for traffic lights according to claim 1, wherein in step S1, the fitting prediction network is established as follows:
establishing a four-layer neural network, wherein the four-layer neural network comprises an input layer, a first middle layer, a second middle layer and an output layer, the input layer and the first middle layer are respectively provided with a neuron, the second middle layer is provided with n neurons, n is equal to the dimension of a speed measurement sequence, the output layer is composed of one neuron, the input is a time variable, and the output is a predicted speed value;
the second intermediate layer is also provided with input excitation, so that the n-dimensional speed measurement sequence of the target vehicle i at the time t state
Is an input stimulus;
the connection weight of the input layer and the first intermediate layer is recorded as w12And the connection weight of the first intermediate layer and the second intermediate layer is recorded as w2xX is more than or equal to 1 and less than or equal to n, and the connection weight of the second intermediate layer and the output layer is recorded as w3qQ is more than or equal to 1 and less than or equal to n, the threshold value of the network neuron adopts a unified threshold value control method, when the threshold value is larger than or equal to 1 and less than or equal to nWhen the input excitation is not all 0, the representative neuron satisfies the output threshold.
3. The intelligent green wave adjustment method for traffic signal lamp as claimed in claim 1, wherein the second processor further adjusts the time of day
Sending to the first processor, the first processor will
And the second interface module is used for sending the time to the display module for displaying so as to remind the time of the green light state of the target vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110015443.8A CN112820123B (en) | 2020-08-27 | 2020-08-27 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010874131.8A CN111739315B (en) | 2020-08-27 | 2020-08-27 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
| CN202110015443.8A CN112820123B (en) | 2020-08-27 | 2020-08-27 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010874131.8A Division CN111739315B (en) | 2020-08-27 | 2020-08-27 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112820123A CN112820123A (en) | 2021-05-18 |
| CN112820123B true CN112820123B (en) | 2022-04-08 |
Family
ID=72658883
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010874131.8A Active CN111739315B (en) | 2020-08-27 | 2020-08-27 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
| CN202110015443.8A Active CN112820123B (en) | 2020-08-27 | 2020-08-27 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010874131.8A Active CN111739315B (en) | 2020-08-27 | 2020-08-27 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111739315B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739315B (en) * | 2020-08-27 | 2021-01-26 | 台州市远行客网络技术有限公司 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
| CN113284344B (en) * | 2021-04-04 | 2022-07-15 | 北方工业大学 | Parallel lane congestion behavior analysis method based on license plate recognition and trajectory data |
| CN113487862A (en) * | 2021-06-30 | 2021-10-08 | 阿波罗智联(北京)科技有限公司 | Green wave speed determination method and device, electronic equipment and storage medium |
| CN114067579B (en) * | 2021-10-21 | 2023-01-03 | 信通院车联网创新中心(成都)有限公司 | Intelligent traffic signal control system and control method thereof |
| CN115050194A (en) * | 2022-06-10 | 2022-09-13 | 绿波速度(浙江)科技有限公司 | Distributed intelligent LED green wave electronic display system applied to general road |
| CN115100882A (en) * | 2022-06-23 | 2022-09-23 | 绿波速度(浙江)科技有限公司 | Green wave traffic control device and method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101703058B1 (en) * | 2016-08-30 | 2017-02-06 | 주식회사 블루시그널 | System for predicting traffic state pattern by analysis of traffic data and predicting method thereof |
| CN106971563B (en) * | 2017-04-01 | 2020-05-19 | 中国科学院深圳先进技术研究院 | Intelligent traffic signal lamp control method and system |
| CN108010343A (en) * | 2017-10-31 | 2018-05-08 | 上海与德科技有限公司 | A kind of control method of traffic lights, control device and control system |
| CN108335508A (en) * | 2018-02-10 | 2018-07-27 | 长安大学 | A kind of green wave speed abductive approach of traffic lights based on V2I and system |
| CN108447281A (en) * | 2018-04-02 | 2018-08-24 | 江苏数慧信息科技有限公司 | Green wave control system |
| CN111739315B (en) * | 2020-08-27 | 2021-01-26 | 台州市远行客网络技术有限公司 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
-
2020
- 2020-08-27 CN CN202010874131.8A patent/CN111739315B/en active Active
- 2020-08-27 CN CN202110015443.8A patent/CN112820123B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111739315B (en) | 2021-01-26 |
| CN112820123A (en) | 2021-05-18 |
| CN111739315A (en) | 2020-10-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112820123B (en) | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp | |
| US11069233B1 (en) | Video-based main road cooperative signal machine control method | |
| US5889477A (en) | Process and system for ascertaining traffic conditions using stationary data collection devices | |
| CN111951549B (en) | Self-adaptive traffic signal lamp control method and system in networked vehicle environment | |
| CN103258427B (en) | Urban expressway traffic real-time monitoring system and method based on information physical network | |
| CN102592451B (en) | Method for detecting road traffic incident based on double-section annular coil detector | |
| CN102708688A (en) | Secondary fuzzy comprehensive discrimination-based urban road condition recognition method | |
| CN113888873B (en) | Expressway accident detection and early warning system and method based on short-time traffic flow | |
| CN110111573B (en) | Congestion vehicle comprehensive scheduling method based on Internet of things | |
| CN113034894A (en) | ETC portal system, and highway section closing early warning method and device | |
| CN113012433A (en) | Vehicle-mounted networking energy-saving auxiliary driving control method and system | |
| US20240046787A1 (en) | Method And System For Traffic Clearance At Signalized Intersections Based On Lidar And Trajectory Prediction | |
| CN115063990A (en) | Dynamic speed limit control method for bottleneck section of highway in mixed traffic flow environment | |
| Roshan et al. | Adaptive traffic control with TinyML | |
| CN102819956B (en) | Detecting method for road traffic accident on basis of single-section annular coil detector | |
| CN111383453B (en) | Traffic signal control on-line simulation and real-time tracking feedback system and operation method | |
| CN114299720A (en) | Public service traffic management method and system based on Internet of things | |
| CN116386337B (en) | Lane dynamic control method and system based on traffic flow prediction | |
| CN111754790B (en) | Ramp entrance traffic control system and method based on radar | |
| CN113505346B (en) | Urban street lamp data processing and combined regulation and control system based on artificial intelligence | |
| CN115862315A (en) | Traffic light control method and device for multisource heterogeneous data flow of smart city | |
| CN114333359A (en) | Artificial intelligence-based self-adaptive traffic signal lamp control method and system | |
| CN114219970A (en) | Image processing method and system for traffic management | |
| CN112071055A (en) | Intelligent expressway operation regulation and control system based on multivariate detection control device | |
| Liu | Refined Judgment of Urban Traffic State Based on Machine Learning and Edge Computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220315 Address after: 410006 No. 4604, 4605, 4606 and 4611, building 15, fangmaoyuan (phase II), No. 1177, Huanhu Road, Tianding street, Yuelu District, Changsha City, Hunan Province Applicant after: Hunan Xiangjiang Zhixin yuntu Technology Co.,Ltd. Address before: 318000 room 1215, building 1, peninsula garden, Tengda Road, Lubei street, Luqiao District, Taizhou City, Zhejiang Province Applicant before: Taizhou yuanxingke Network Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |